The L40S is newer and has 50% more memory, with about the same bandwidth.
At a glance
Memory
50% more on L40S
- L40S
- 48 GB
- V100
- 32 GB
Memory bandwidth
Within 5%
- L40S
- 864 GB/s
- V100
- 900 GB/s
Cheapest on-demand
75% cheaper on V100
- L40S
- $0.55 /GPU/hr
- V100
- $0.14 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | L40S | V100 | Difference |
|---|---|---|---|
| On-demand | $1.64 /GPU/hr from $0.55 | $2.14 /GPU/hr from $0.14 | 23% cheaper on L40S |
| Reserved | $1.09 /GPU/hr from $0.61 (12 mo) | $1.52 /GPU/hr from $0.22 (24 mo) | 28% cheaper on L40S |
| Spot | $1.11 /GPU/hr from $0.74 | $0.40 /GPU/hr from $0.12 | 64% cheaper on V100 |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. Verify before provisioning. More on how we price.
Price history
L40S vs V100 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | L40S | V100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 48 GB GDDR6 | 32 GB HBM2 | 50% more on L40S |
| Bandwidth | 864 GB/s | 900 GB/s | Within 5% |
| Bus width | 384-bit | 4,096-bit | 11x wider on V100 |
| Compute · dense | |||
| FP8 | 733 TFLOPS | Not supported | L40S only |
| FP16 / BF16 | 362.1 TFLOPS | 125 TFLOPS | 2.9x higher on L40S |
| INT8 | 733 TOPS | ||
| FP32 | 91.6 TFLOPS | 15.7 TFLOPS | 5.8x higher on L40S |
| FP64 | Not supported | 7.8 TFLOPS | V100 only |
| Platform | |||
| Interconnect | PCIe only | NVLink 300 GB/s | NVLink on V100 only |
| Board power | 350 W | 300 W | 17% higher on L40S |
| Released | Q3 2023 | Q2 2017 | 6 years newer on L40S |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP16FP32FP64INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: L40S datasheet and V100 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | L40S | V100 |
|---|---|---|
Sesterce
France
|
$0.97 /GPU/hr On-demand | $2.57 /GPU/hr On-demand |
Runcrate
USA
|
$1.14 /GPU/hr On-demand PCIe | $3.04 /GPU/hr On-demand NVL |
Novita
USA
|
$0.55 /GPU/hr On-demand | -- |
GPU.ai
UAE
|
$0.80 /GPU/hr On-demand | -- |
Packet·ai
USA
|
$0.92 /GPU/hr On-demand | -- |
Massed Compute
USA
|
$0.97 /GPU/hr On-demand | -- |
Runpod
USA
|
$1.09 /GPU/hr On-demand | -- |
UpCloud
Finland
|
$1.19 /GPU/hr On-demand | -- |
HyperAI
Hong Kong
|
-- | $0.14 /GPU/hr On-demand |
Verda
Finland
|
-- | $0.12 /GPU/hr Spot |
Geodd
USA
|
-- | $0.16 /GPU/hr On-demand |
TensorDock
Distributed
|
-- | $0.28 /GPU/hr On-demand SXM |
Cyfuture AI
India
|
-- | $0.55 /GPU/hr On-demand |
OVH
France
|
-- | $0.77 /GPU/hr On-demand |
37 providers list the L40S and 19 the V100. Every listing is on the L40S page and the V100 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia L40S was last updated on Sept. 14, 2026, and for Nvidia V100 on Sept. 14, 2026.